{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3CTVALZJI4O45RR2TFY63TG4RY","short_pith_number":"pith:3CTVALZJ","canonical_record":{"source":{"id":"2303.16839","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T16:42:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"806a32304bc0c48552c92d6d9fc01eff56c8b6fdff70968428be3cf8a0a2fe02","abstract_canon_sha256":"3919696c311721cfa1ba4c36f6af624475dd05a5f421b106516be83fa273ead8"},"schema_version":"1.0"},"canonical_sha256":"d8a7502f29471dcec63a9971edccdc8e15c5d07a3a4872f3693f6b97abe8beb8","source":{"kind":"arxiv","id":"2303.16839","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16839","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16839v3","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16839","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_12","alias_value":"3CTVALZJI4O4","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_16","alias_value":"3CTVALZJI4O45RR2","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_8","alias_value":"3CTVALZJ","created_at":"2026-07-05T06:39:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3CTVALZJI4O45RR2TFY63TG4RY","target":"record","payload":{"canonical_record":{"source":{"id":"2303.16839","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T16:42:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"806a32304bc0c48552c92d6d9fc01eff56c8b6fdff70968428be3cf8a0a2fe02","abstract_canon_sha256":"3919696c311721cfa1ba4c36f6af624475dd05a5f421b106516be83fa273ead8"},"schema_version":"1.0"},"canonical_sha256":"d8a7502f29471dcec63a9971edccdc8e15c5d07a3a4872f3693f6b97abe8beb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:33.679170Z","signature_b64":"g9ZCtS42XWxGYqeNQ3JfJ8yrvDIWJ9odH8jdYketsTnep3pl0dtguP9MGv7vVkvkFRly4AloJU7cBDyOfeP2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a7502f29471dcec63a9971edccdc8e15c5d07a3a4872f3693f6b97abe8beb8","last_reissued_at":"2026-07-05T06:39:33.678665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:33.678665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.16839","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:39:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IArrp5jCemuYif4QNSQ1XGH64aBi5vDk+8z4dmcOSafw3d5KJqcY7+C4xY/p17CiVEiisiqsZAeKmO3/t6nDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:16:10.813365Z"},"content_sha256":"a95dcb0b365ef917953848eafb4a3ee092d3cc7f3edf5076782e5e234e371db7","schema_version":"1.0","event_id":"sha256:a95dcb0b365ef917953848eafb4a3ee092d3cc7f3edf5076782e5e234e371db7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3CTVALZJI4O45RR2TFY63TG4RY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Ogale, AJ Piergiovanni, Andrew Dai, Anelia Angelova, Ben Caine, Claire Cui, Dahun Kim, Luowei Zhou, Weicheng Kuo, Wei Li, Xiyang Luo, Zhifeng Chen","submitted_at":"2023-03-29T16:42:30Z","abstract_excerpt":"The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is abl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16839","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.16839/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:39:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bxqd+HovyTIUzsUbV0jITHC16jaup/EV4pi0UlohXJMZgVfovc5Kd7qciR8D/K5ClIiueKdevKgSMA5cK1D2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:16:10.813854Z"},"content_sha256":"a6156dc26bbd13bdd1016b4fcf3d03f0c6808f32245fb692f63b5404ff499544","schema_version":"1.0","event_id":"sha256:a6156dc26bbd13bdd1016b4fcf3d03f0c6808f32245fb692f63b5404ff499544"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CTVALZJI4O45RR2TFY63TG4RY/bundle.json","state_url":"https://pith.science/pith/3CTVALZJI4O45RR2TFY63TG4RY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CTVALZJI4O45RR2TFY63TG4RY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T10:16:10Z","links":{"resolver":"https://pith.science/pith/3CTVALZJI4O45RR2TFY63TG4RY","bundle":"https://pith.science/pith/3CTVALZJI4O45RR2TFY63TG4RY/bundle.json","state":"https://pith.science/pith/3CTVALZJI4O45RR2TFY63TG4RY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CTVALZJI4O45RR2TFY63TG4RY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3CTVALZJI4O45RR2TFY63TG4RY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3919696c311721cfa1ba4c36f6af624475dd05a5f421b106516be83fa273ead8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T16:42:30Z","title_canon_sha256":"806a32304bc0c48552c92d6d9fc01eff56c8b6fdff70968428be3cf8a0a2fe02"},"schema_version":"1.0","source":{"id":"2303.16839","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16839","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16839v3","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16839","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_12","alias_value":"3CTVALZJI4O4","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_16","alias_value":"3CTVALZJI4O45RR2","created_at":"2026-07-05T06:39:33Z"},{"alias_kind":"pith_short_8","alias_value":"3CTVALZJ","created_at":"2026-07-05T06:39:33Z"}],"graph_snapshots":[{"event_id":"sha256:a6156dc26bbd13bdd1016b4fcf3d03f0c6808f32245fb692f63b5404ff499544","target":"graph","created_at":"2026-07-05T06:39:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.16839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is abl","authors_text":"Abhijit Ogale, AJ Piergiovanni, Andrew Dai, Anelia Angelova, Ben Caine, Claire Cui, Dahun Kim, Luowei Zhou, Weicheng Kuo, Wei Li, Xiyang Luo, Zhifeng Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T16:42:30Z","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16839","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a95dcb0b365ef917953848eafb4a3ee092d3cc7f3edf5076782e5e234e371db7","target":"record","created_at":"2026-07-05T06:39:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3919696c311721cfa1ba4c36f6af624475dd05a5f421b106516be83fa273ead8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T16:42:30Z","title_canon_sha256":"806a32304bc0c48552c92d6d9fc01eff56c8b6fdff70968428be3cf8a0a2fe02"},"schema_version":"1.0","source":{"id":"2303.16839","kind":"arxiv","version":3}},"canonical_sha256":"d8a7502f29471dcec63a9971edccdc8e15c5d07a3a4872f3693f6b97abe8beb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8a7502f29471dcec63a9971edccdc8e15c5d07a3a4872f3693f6b97abe8beb8","first_computed_at":"2026-07-05T06:39:33.678665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:33.678665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g9ZCtS42XWxGYqeNQ3JfJ8yrvDIWJ9odH8jdYketsTnep3pl0dtguP9MGv7vVkvkFRly4AloJU7cBDyOfeP2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:33.679170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16839","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a95dcb0b365ef917953848eafb4a3ee092d3cc7f3edf5076782e5e234e371db7","sha256:a6156dc26bbd13bdd1016b4fcf3d03f0c6808f32245fb692f63b5404ff499544"],"state_sha256":"64eff2fe771120187cf5096f34defbe9050567200ca4089ac50d45a3ad97843d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oymggKyPcNjiK53iwzn9/mz71q2WhUApz8GTCThcqmGEE3lusOiOIGoNefvjdwiK91snIYS/Ljy1hirQpVSxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:16:10.817213Z","bundle_sha256":"ea1b17d073c46d79288bcf3280a2269b67e719b90e72adc7da5350a1e9a2b18f"}}